Merge branch 'turbostat' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux

Pull turbostat update from Len Brown:
 "Updates to the turbostat utility.

  Just one kernel dependency in this batch -- added a #define to
  msr-index.h"

* 'turbostat' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux:
  tools/power turbostat: correct dumped pkg-cstate-limit value
  tools/power turbostat: calculate TSC frequency from CPUID(0x15) on SKL
  tools/power turbostat: correct DRAM RAPL units on recent Xeon processors
  tools/power turbostat: Initial Skylake support
  tools/power turbostat: Use $(CURDIR) instead of $(PWD) and add support for O= option in Makefile
  tools/power turbostat: modprobe msr, if needed
  tools/power turbostat: dump MSR_TURBO_RATIO_LIMIT2
  tools/power turbostat: use new MSR_TURBO_RATIO_LIMIT names
  x86 msr-index: define MSR_TURBO_RATIO_LIMIT,1,2
  tools/power turbostat: label base frequency
  tools/power turbostat: update PERF_LIMIT_REASONS decoding
  tools/power turbostat: simplify default output

3 files changed, 419 insertions, 161 deletions

diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index d1b3a361e526..4039854560d0 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -1,8 +1,12 @@
 CC		= $(CROSS_COMPILE)gcc
-BUILD_OUTPUT	:= $(PWD)
+BUILD_OUTPUT	:= $(CURDIR)
 PREFIX		:= /usr
 DESTDIR		:=
 
+ifeq ("$(origin O)", "command line")
+	BUILD_OUTPUT := $(O)
+endif
+
 turbostat : turbostat.c
 CFLAGS +=	-Wall
 CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index feea7ad9500b..05b8fc38dc8b 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -20,9 +20,11 @@ upon its completion.
 The second method is to omit the command,
 and turbostat displays statistics every 5 seconds.
 The 5-second interval can be changed using the --interval option.
-
+.PP
 Some information is not available on older processors.
 .SS Options
+Options can be specified with a single or double '-', and only as much of the option
+name as necessary to disambiguate it from others is necessary.  Note that options are case-sensitive.
 \fB--Counter MSR#\fP shows the delta of the specified 64-bit MSR counter.
 .PP
 \fB--counter MSR#\fP shows the delta of the specified 32-bit MSR counter.
@@ -55,16 +57,20 @@ more than once may also enable internal turbostat debug information.
 The \fBcommand\fP parameter forks \fBcommand\fP, and upon its exit,
 displays the statistics gathered since it was forked.
 .PP
-.SH FIELD DESCRIPTIONS
+.SH DEFAULT FIELD DESCRIPTIONS
 .nf
-\fBPackage\fP processor package number.
-\fBCore\fP processor core number.
-\fBCPU\fP Linux CPU (logical processor) number.
-Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology.
+\fBCPU\fP Linux CPU (logical processor) number.  Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together.
 \fBAVG_MHz\fP number of cycles executed divided by time elapsed.
 \fB%Busy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
 \fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state).
 \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval.
+.fi
+.PP
+.SH DEBUG FIELD DESCRIPTIONS
+.nf
+\fBPackage\fP processor package number.
+\fBCore\fP processor core number.
+Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT).
 \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.
 \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
 \fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
@@ -81,63 +87,76 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T
 Without any parameters, turbostat displays statistics ever 5 seconds.
 (override interval with "-i sec" option, or specify a command
 for turbostat to fork).
+.nf
+[root@hsw]# ./turbostat
+     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz
+       -     488   12.51    3898    3498
+       0       0    0.01    3885    3498
+       4    3897   99.99    3898    3498
+       1       0    0.00    3861    3498
+       5       0    0.00    3882    3498
+       2       1    0.02    3894    3498
+       6       2    0.06    3898    3498
+       3       0    0.00    3849    3498
+       7       0    0.00    3877    3498
+
+.fi
+.SH DEBUG EXAMPLE
+The "--debug" option prints additional system information before measurements:
 
 The first row of statistics is a summary for the entire system.
 For residency % columns, the summary is a weighted average.
 For Temperature columns, the summary is the column maximum.
 For Watts columns, the summary is a system total.
 Subsequent rows show per-CPU statistics.
-
-.nf
-[root@ivy]# ./turbostat
-    Core     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt 
-       -       -       6    0.36    1596    3492       0    0.59    0.01   99.04    0.00      23      24   23.82    0.01   72.47    0.00    6.40    1.01    0.00
-       0       0       9    0.58    1596    3492       0    0.28    0.01   99.13    0.00      23      24   23.82    0.01   72.47    0.00    6.40    1.01    0.00
-       0       4       1    0.07    1596    3492       0    0.79
-       1       1      10    0.65    1596    3492       0    0.59    0.00   98.76    0.00      23
-       1       5       5    0.28    1596    3492       0    0.95
-       2       2      10    0.66    1596    3492       0    0.41    0.01   98.92    0.00      23
-       2       6       2    0.10    1597    3492       0    0.97
-       3       3       3    0.20    1596    3492       0    0.44    0.00   99.37    0.00      23
-       3       7       5    0.31    1596    3492       0    0.33
-.fi
-.SH DEBUG EXAMPLE
-The "--debug" option prints additional system information before measurements:
-
 .nf
-turbostat version 4.0 10-Feb, 2015 - Len Brown <lenb@kernel.org>
-CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3a:9 (6:58:9)
+turbostat version 4.1 10-Feb, 2015 - Len Brown <lenb@kernel.org>
+CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3c:3 (6:60:3)
 CPUID(6): APERF, DTS, PTM, EPB
-RAPL: 851 sec. Joule Counter Range, at 77 Watts
-cpu0: MSR_NHM_PLATFORM_INFO: 0x81010f0012300
-16 * 100 = 1600 MHz max efficiency
+RAPL: 3121 sec. Joule Counter Range, at 84 Watts
+cpu0: MSR_NHM_PLATFORM_INFO: 0x80838f3012300
+8 * 100 = 800 MHz max efficiency
 35 * 100 = 3500 MHz TSC frequency
-cpu0: MSR_IA32_POWER_CTL: 0x0014005d (C1E auto-promotion: DISabled)
-cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008402 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, locked: pkg-cstate-limit=2: pc6n)
+cpu0: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled)
+cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0)
 cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727
 37 * 100 = 3700 MHz max turbo 4 active cores
 38 * 100 = 3800 MHz max turbo 3 active cores
 39 * 100 = 3900 MHz max turbo 2 active cores
 39 * 100 = 3900 MHz max turbo 1 active cores
 cpu0: MSR_IA32_ENERGY_PERF_BIAS: 0x00000006 (balanced)
-cpu0: MSR_RAPL_POWER_UNIT: 0x000a1003 (0.125000 Watts, 0.000015 Joules, 0.000977 sec.)
-cpu0: MSR_PKG_POWER_INFO: 0x01e00268 (77 W TDP, RAPL 60 - 0 W, 0.000000 sec.)
-cpu0: MSR_PKG_POWER_LIMIT: 0x30000148268 (UNlocked)
-cpu0: PKG Limit #1: ENabled (77.000000 Watts, 1.000000 sec, clamp DISabled)
-cpu0: PKG Limit #2: DISabled (96.000000 Watts, 0.000977* sec, clamp DISabled)
+cpu0: MSR_CORE_PERF_LIMIT_REASONS, 0x31200000 (Active: ) (Logged: Auto-HWP, Amps, MultiCoreTurbo, Transitions, )
+cpu0: MSR_GFX_PERF_LIMIT_REASONS, 0x00000000 (Active: ) (Logged: )
+cpu0: MSR_RING_PERF_LIMIT_REASONS, 0x0d000000 (Active: ) (Logged: Amps, PkgPwrL1, PkgPwrL2, )
+cpu0: MSR_RAPL_POWER_UNIT: 0x000a0e03 (0.125000 Watts, 0.000061 Joules, 0.000977 sec.)
+cpu0: MSR_PKG_POWER_INFO: 0x000002a0 (84 W TDP, RAPL 0 - 0 W, 0.000000 sec.)
+cpu0: MSR_PKG_POWER_LIMIT: 0x428348001a82a0 (UNlocked)
+cpu0: PKG Limit #1: ENabled (84.000000 Watts, 8.000000 sec, clamp DISabled)
+cpu0: PKG Limit #2: ENabled (105.000000 Watts, 0.002441* sec, clamp DISabled)
 cpu0: MSR_PP0_POLICY: 0
 cpu0: MSR_PP0_POWER_LIMIT: 0x00000000 (UNlocked)
 cpu0: Cores Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
 cpu0: MSR_PP1_POLICY: 0
 cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked)
 cpu0: GFX Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
-cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00691400 (105 C)
-cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884e0000 (27 C)
-cpu0: MSR_IA32_THERM_STATUS: 0x88580000 (17 C +/- 1)
-cpu1: MSR_IA32_THERM_STATUS: 0x885a0000 (15 C +/- 1)
-cpu2: MSR_IA32_THERM_STATUS: 0x88570000 (18 C +/- 1)
-cpu3: MSR_IA32_THERM_STATUS: 0x884e0000 (27 C +/- 1)
- ...
+cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00641400 (100 C)
+cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x88340800 (48 C)
+cpu0: MSR_IA32_THERM_STATUS: 0x88340000 (48 C +/- 1)
+cpu1: MSR_IA32_THERM_STATUS: 0x88440000 (32 C +/- 1)
+cpu2: MSR_IA32_THERM_STATUS: 0x88450000 (31 C +/- 1)
+cpu3: MSR_IA32_THERM_STATUS: 0x88490000 (27 C +/- 1)
+    Core     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp PkgWatt CorWatt GFXWatt
+       -       -     493   12.64    3898    3498       0   12.64    0.00    0.00   74.72      47      47   21.62   13.74    0.00
+       0       0       4    0.11    3894    3498       0   99.89    0.00    0.00    0.00      47      47   21.62   13.74    0.00
+       0       4    3897   99.98    3898    3498       0    0.02
+       1       1       7    0.17    3887    3498       0    0.04    0.00    0.00   99.79      32
+       1       5       0    0.00    3885    3498       0    0.21
+       2       2      29    0.76    3895    3498       0    0.10    0.01    0.01   99.13      32
+       2       6       2    0.06    3896    3498       0    0.80
+       3       3       1    0.02    3832    3498       0    0.03    0.00    0.00   99.95      28
+       3       7       0    0.00    3879    3498       0    0.04
+^C
+
 .fi
 The \fBmax efficiency\fP frequency, a.k.a. Low Frequency Mode, is the frequency
 available at the minimum package voltage.  The \fBTSC frequency\fP is the base
@@ -147,6 +166,9 @@ should be sustainable on all CPUs indefinitely, given nominal power and cooling.
 The remaining rows show what maximum turbo frequency is possible
 depending on the number of idle cores.  Note that not all information is
 available on all processors.
+.PP
+The --debug option adds additional columns to the measurement ouput, including CPU idle power-state residency processor temperature sensor readinds.
+See the field definitions above.
 .SH FORK EXAMPLE
 If turbostat is invoked with a command, it will fork that command
 and output the statistics gathered when the command exits.
@@ -154,27 +176,23 @@ eg. Here a cycle soaker is run on 1 CPU (see %c0) for a few seconds
 until ^C while the other CPUs are mostly idle:
 
 .nf
-root@ivy: turbostat cat /dev/zero > /dev/null
+root@hsw: turbostat cat /dev/zero > /dev/null
 ^C
-    Core     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt 
-       -       -     496   12.75    3886    3492       0   13.16    0.04   74.04    0.00      36      36    0.00    0.00    0.00    0.00   23.15   17.65    0.00
-       0       0      22    0.57    3830    3492       0    0.83    0.02   98.59    0.00      27      36    0.00    0.00    0.00    0.00   23.15   17.65    0.00
-       0       4       9    0.24    3829    3492       0    1.15
-       1       1       4    0.09    3783    3492       0   99.91    0.00    0.00    0.00      36
-       1       5    3880   99.82    3888    3492       0    0.18
-       2       2      17    0.44    3813    3492       0    0.77    0.04   98.75    0.00      28
-       2       6      12    0.32    3823    3492       0    0.89
-       3       3      16    0.43    3844    3492       0    0.63    0.11   98.84    0.00      30
-       3       7       4    0.11    3827    3492       0    0.94
-30.372243 sec
+     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz
+       -     482   12.51    3854    3498
+       0       0    0.01    1960    3498
+       4       0    0.00    2128    3498
+       1       0    0.00    3003    3498
+       5    3854   99.98    3855    3498
+       2       0    0.01    3504    3498
+       6       3    0.08    3884    3498
+       3       0    0.00    2553    3498
+       7       0    0.00    2126    3498
+10.783983 sec
 
 .fi
-Above the cycle soaker drives cpu5 up its 3.8 GHz turbo limit
-while the other processors are generally in various states of idle.
-
-Note that cpu1 and cpu5 are HT siblings within core1.
-As cpu5 is very busy, it prevents its sibling, cpu1,
-from entering a c-state deeper than c1.
+Above the cycle soaker drives cpu5 up its 3.9 GHz turbo limit.
+The first row shows the average MHz and %Busy across all the processors in the system.
 
 Note that the Avg_MHz column reflects the total number of cycles executed
 divided by the measurement interval.  If the %Busy column is 100%,
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 2d089cac8580..bac98ca3d4ca 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -57,6 +57,7 @@ unsigned int do_pc3;
 unsigned int do_pc6;
 unsigned int do_pc7;
 unsigned int do_c8_c9_c10;
+unsigned int do_skl_residency;
 unsigned int do_slm_cstates;
 unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
@@ -65,8 +66,6 @@ unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int has_invariant_tsc;
 unsigned int do_nhm_platform_info;
-unsigned int do_nhm_turbo_ratio_limit;
-unsigned int do_ivt_turbo_ratio_limit;
 unsigned int extra_msr_offset32;
 unsigned int extra_msr_offset64;
 unsigned int extra_delta_offset32;
@@ -84,11 +83,14 @@ unsigned int do_dts;
 unsigned int do_ptm;
 unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
-double rapl_power_units, rapl_energy_units, rapl_time_units;
+double rapl_power_units, rapl_time_units;
+double rapl_dram_energy_units, rapl_energy_units;
 double rapl_joule_counter_range;
 unsigned int do_core_perf_limit_reasons;
 unsigned int do_gfx_perf_limit_reasons;
 unsigned int do_ring_perf_limit_reasons;
+unsigned int crystal_hz;
+unsigned long long tsc_hz;
 
 #define RAPL_PKG		(1 << 0)
 					/* 0x610 MSR_PKG_POWER_LIMIT */
@@ -101,18 +103,18 @@ unsigned int do_ring_perf_limit_reasons;
 #define RAPL_DRAM		(1 << 3)
 					/* 0x618 MSR_DRAM_POWER_LIMIT */
 					/* 0x619 MSR_DRAM_ENERGY_STATUS */
-					/* 0x61c MSR_DRAM_POWER_INFO */
 #define RAPL_DRAM_PERF_STATUS	(1 << 4)
 					/* 0x61b MSR_DRAM_PERF_STATUS */
+#define RAPL_DRAM_POWER_INFO	(1 << 5)
+					/* 0x61c MSR_DRAM_POWER_INFO */
 
-#define RAPL_CORES		(1 << 5)
+#define RAPL_CORES		(1 << 6)
 					/* 0x638 MSR_PP0_POWER_LIMIT */
 					/* 0x639 MSR_PP0_ENERGY_STATUS */
-#define RAPL_CORE_POLICY	(1 << 6)
+#define RAPL_CORE_POLICY	(1 << 7)
 					/* 0x63a MSR_PP0_POLICY */
 
-
-#define RAPL_GFX		(1 << 7)
+#define RAPL_GFX		(1 << 8)
 					/* 0x640 MSR_PP1_POWER_LIMIT */
 					/* 0x641 MSR_PP1_ENERGY_STATUS */
 					/* 0x642 MSR_PP1_POLICY */
@@ -159,6 +161,10 @@ struct pkg_data {
 	unsigned long long pc8;
 	unsigned long long pc9;
 	unsigned long long pc10;
+	unsigned long long pkg_wtd_core_c0;
+	unsigned long long pkg_any_core_c0;
+	unsigned long long pkg_any_gfxe_c0;
+	unsigned long long pkg_both_core_gfxe_c0;
 	unsigned int package_id;
 	unsigned int energy_pkg;	/* MSR_PKG_ENERGY_STATUS */
 	unsigned int energy_dram;	/* MSR_DRAM_ENERGY_STATUS */
@@ -292,8 +298,7 @@ void print_header(void)
 	if (has_aperf)
 		outp += sprintf(outp, " Bzy_MHz");
 	outp += sprintf(outp, " TSC_MHz");
-	if (do_smi)
-		outp += sprintf(outp, "     SMI");
+
 	if (extra_delta_offset32)
 		outp += sprintf(outp, "  count 0x%03X", extra_delta_offset32);
 	if (extra_delta_offset64)
@@ -302,6 +307,13 @@ void print_header(void)
 		outp += sprintf(outp, "   MSR 0x%03X", extra_msr_offset32);
 	if (extra_msr_offset64)
 		outp += sprintf(outp, "           MSR 0x%03X", extra_msr_offset64);
+
+	if (!debug)
+		goto done;
+
+	if (do_smi)
+		outp += sprintf(outp, "     SMI");
+
 	if (do_nhm_cstates)
 		outp += sprintf(outp, "  CPU%%c1");
 	if (do_nhm_cstates && !do_slm_cstates)
@@ -316,6 +328,13 @@ void print_header(void)
 	if (do_ptm)
 		outp += sprintf(outp, "  PkgTmp");
 
+	if (do_skl_residency) {
+		outp += sprintf(outp, " Totl%%C0");
+		outp += sprintf(outp, "  Any%%C0");
+		outp += sprintf(outp, "  GFX%%C0");
+		outp += sprintf(outp, " CPUGFX%%");
+	}
+
 	if (do_pc2)
 		outp += sprintf(outp, " Pkg%%pc2");
 	if (do_pc3)
@@ -359,6 +378,7 @@ void print_header(void)
 		outp += sprintf(outp, "   time");
 
 	}
+    done:
 	outp += sprintf(outp, "\n");
 }
 
@@ -396,6 +416,12 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 
 	if (p) {
 		outp += sprintf(outp, "package: %d\n", p->package_id);
+
+		outp += sprintf(outp, "Weighted cores: %016llX\n", p->pkg_wtd_core_c0);
+		outp += sprintf(outp, "Any cores: %016llX\n", p->pkg_any_core_c0);
+		outp += sprintf(outp, "Any GFX: %016llX\n", p->pkg_any_gfxe_c0);
+		outp += sprintf(outp, "CPU + GFX: %016llX\n", p->pkg_both_core_gfxe_c0);
+
 		outp += sprintf(outp, "pc2: %016llX\n", p->pc2);
 		if (do_pc3)
 			outp += sprintf(outp, "pc3: %016llX\n", p->pc3);
@@ -487,10 +513,6 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	/* TSC_MHz */
 	outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
 
-	/* SMI */
-	if (do_smi)
-		outp += sprintf(outp, "%8d", t->smi_count);
-
 	/* delta */
 	if (extra_delta_offset32)
 		outp += sprintf(outp, "  %11llu", t->extra_delta32);
@@ -506,6 +528,13 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (extra_msr_offset64)
 		outp += sprintf(outp, "  0x%016llx", t->extra_msr64);
 
+	if (!debug)
+		goto done;
+
+	/* SMI */
+	if (do_smi)
+		outp += sprintf(outp, "%8d", t->smi_count);
+
 	if (do_nhm_cstates) {
 		if (!skip_c1)
 			outp += sprintf(outp, "%8.2f", 100.0 * t->c1/t->tsc);
@@ -531,9 +560,18 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		goto done;
 
+	/* PkgTmp */
 	if (do_ptm)
 		outp += sprintf(outp, "%8d", p->pkg_temp_c);
 
+	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
+	if (do_skl_residency) {
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_any_core_c0/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_any_gfxe_c0/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_both_core_gfxe_c0/t->tsc);
+	}
+
 	if (do_pc2)
 		outp += sprintf(outp, "%8.2f", 100.0 * p->pc2/t->tsc);
 	if (do_pc3)
@@ -565,7 +603,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		if (do_rapl & RAPL_GFX)
 			outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float);
 		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, fmt8, p->energy_dram * rapl_energy_units / interval_float);
+			outp += sprintf(outp, fmt8, p->energy_dram * rapl_dram_energy_units / interval_float);
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
@@ -582,7 +620,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 					p->energy_gfx * rapl_energy_units);
 		if (do_rapl & RAPL_DRAM)
 			outp += sprintf(outp, fmt8,
-					p->energy_dram * rapl_energy_units);
+					p->energy_dram * rapl_dram_energy_units);
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
@@ -636,6 +674,13 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_
 void
 delta_package(struct pkg_data *new, struct pkg_data *old)
 {
+
+	if (do_skl_residency) {
+		old->pkg_wtd_core_c0 = new->pkg_wtd_core_c0 - old->pkg_wtd_core_c0;
+		old->pkg_any_core_c0 = new->pkg_any_core_c0 - old->pkg_any_core_c0;
+		old->pkg_any_gfxe_c0 = new->pkg_any_gfxe_c0 - old->pkg_any_gfxe_c0;
+		old->pkg_both_core_gfxe_c0 = new->pkg_both_core_gfxe_c0 - old->pkg_both_core_gfxe_c0;
+	}
 	old->pc2 = new->pc2 - old->pc2;
 	if (do_pc3)
 		old->pc3 = new->pc3 - old->pc3;
@@ -782,6 +827,11 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	c->c7 = 0;
 	c->core_temp_c = 0;
 
+	p->pkg_wtd_core_c0 = 0;
+	p->pkg_any_core_c0 = 0;
+	p->pkg_any_gfxe_c0 = 0;
+	p->pkg_both_core_gfxe_c0 = 0;
+
 	p->pc2 = 0;
 	if (do_pc3)
 		p->pc3 = 0;
@@ -826,6 +876,13 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		return 0;
 
+	if (do_skl_residency) {
+		average.packages.pkg_wtd_core_c0 += p->pkg_wtd_core_c0;
+		average.packages.pkg_any_core_c0 += p->pkg_any_core_c0;
+		average.packages.pkg_any_gfxe_c0 += p->pkg_any_gfxe_c0;
+		average.packages.pkg_both_core_gfxe_c0 += p->pkg_both_core_gfxe_c0;
+	}
+
 	average.packages.pc2 += p->pc2;
 	if (do_pc3)
 		average.packages.pc3 += p->pc3;
@@ -873,6 +930,13 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	average.cores.c6 /= topo.num_cores;
 	average.cores.c7 /= topo.num_cores;
 
+	if (do_skl_residency) {
+		average.packages.pkg_wtd_core_c0 /= topo.num_packages;
+		average.packages.pkg_any_core_c0 /= topo.num_packages;
+		average.packages.pkg_any_gfxe_c0 /= topo.num_packages;
+		average.packages.pkg_both_core_gfxe_c0 /= topo.num_packages;
+	}
+
 	average.packages.pc2 /= topo.num_packages;
 	if (do_pc3)
 		average.packages.pc3 /= topo.num_packages;
@@ -979,6 +1043,16 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		return 0;
 
+	if (do_skl_residency) {
+		if (get_msr(cpu, MSR_PKG_WEIGHTED_CORE_C0_RES, &p->pkg_wtd_core_c0))
+			return -10;
+		if (get_msr(cpu, MSR_PKG_ANY_CORE_C0_RES, &p->pkg_any_core_c0))
+			return -11;
+		if (get_msr(cpu, MSR_PKG_ANY_GFXE_C0_RES, &p->pkg_any_gfxe_c0))
+			return -12;
+		if (get_msr(cpu, MSR_PKG_BOTH_CORE_GFXE_C0_RES, &p->pkg_both_core_gfxe_c0))
+			return -13;
+	}
 	if (do_pc3)
 		if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3))
 			return -9;
@@ -1055,49 +1129,77 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 #define PCL_6R 9 /* PC6 Retention */
 #define PCL__7 10 /* PC7 */
 #define PCL_7S 11 /* PC7 Shrink */
-#define PCLUNL 12 /* Unlimited */
+#define PCL__8 12 /* PC8 */
+#define PCL__9 13 /* PC9 */
+#define PCLUNL 14 /* Unlimited */
 
 int pkg_cstate_limit = PCLUKN;
 char *pkg_cstate_limit_strings[] = { "reserved", "unknown", "pc0", "pc1", "pc2",
-	"pc3", "pc4", "pc6", "pc6n", "pc6r", "pc7", "pc7s", "unlimited"};
+	"pc3", "pc4", "pc6", "pc6n", "pc6r", "pc7", "pc7s", "pc8", "pc9", "unlimited"};
 
-int nhm_pkg_cstate_limits[8] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLUNL};
-int snb_pkg_cstate_limits[8] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL};
-int hsw_pkg_cstate_limits[8] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, PCLRSV, PCLUNL};
-int slv_pkg_cstate_limits[8] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7};
-int amt_pkg_cstate_limits[8] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7};
-int phi_pkg_cstate_limits[8] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL};
+int nhm_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int snb_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int hsw_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, PCL__8, PCL__9, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 
-void print_verbose_header(void)
+static void
+dump_nhm_platform_info(void)
 {
 	unsigned long long msr;
 	unsigned int ratio;
 
-	if (!do_nhm_platform_info)
-		return;
-
 	get_msr(0, MSR_NHM_PLATFORM_INFO, &msr);
 
 	fprintf(stderr, "cpu0: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", msr);
 
 	ratio = (msr >> 40) & 0xFF;
-	fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency\n",
+	fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency frequency\n",
 		ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
-	fprintf(stderr, "%d * %.0f = %.0f MHz TSC frequency\n",
+	fprintf(stderr, "%d * %.0f = %.0f MHz base frequency\n",
 		ratio, bclk, ratio * bclk);
 
 	get_msr(0, MSR_IA32_POWER_CTL, &msr);
 	fprintf(stderr, "cpu0: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
 		msr, msr & 0x2 ? "EN" : "DIS");
 
-	if (!do_ivt_turbo_ratio_limit)
-		goto print_nhm_turbo_ratio_limits;
+	return;
+}
+
+static void
+dump_hsw_turbo_ratio_limits(void)
+{
+	unsigned long long msr;
+	unsigned int ratio;
+
+	get_msr(0, MSR_TURBO_RATIO_LIMIT2, &msr);
+
+	fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", msr);
+
+	ratio = (msr >> 8) & 0xFF;
+	if (ratio)
+		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 18 active cores\n",
+			ratio, bclk, ratio * bclk);
+
+	ratio = (msr >> 0) & 0xFF;
+	if (ratio)
+		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 17 active cores\n",
+			ratio, bclk, ratio * bclk);
+	return;
+}
+
+static void
+dump_ivt_turbo_ratio_limits(void)
+{
+	unsigned long long msr;
+	unsigned int ratio;
 
-	get_msr(0, MSR_IVT_TURBO_RATIO_LIMIT, &msr);
+	get_msr(0, MSR_TURBO_RATIO_LIMIT1, &msr);
 
-	fprintf(stderr, "cpu0: MSR_IVT_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
+	fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", msr);
 
 	ratio = (msr >> 56) & 0xFF;
 	if (ratio)
@@ -1138,30 +1240,18 @@ void print_verbose_header(void)
 	if (ratio)
 		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 9 active cores\n",
 			ratio, bclk, ratio * bclk);
+	return;
+}
 
-print_nhm_turbo_ratio_limits:
-	get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
-
-#define SNB_C1_AUTO_UNDEMOTE              (1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE              (1UL << 28)
-
-	fprintf(stderr, "cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", msr);
-
-	fprintf(stderr, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
-		(msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
-		(msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "",
-		(msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "",
-		(msr & NHM_C1_AUTO_DEMOTE) ? "demote-C1, " : "",
-		(msr & (1 << 15)) ? "" : "UN",
-		(unsigned int)msr & 7,
-		pkg_cstate_limit_strings[pkg_cstate_limit]);
-
-	if (!do_nhm_turbo_ratio_limit)
-		return;
+static void
+dump_nhm_turbo_ratio_limits(void)
+{
+	unsigned long long msr;
+	unsigned int ratio;
 
-	get_msr(0, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
+	get_msr(0, MSR_TURBO_RATIO_LIMIT, &msr);
 
-	fprintf(stderr, "cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
+	fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
 
 	ratio = (msr >> 56) & 0xFF;
 	if (ratio)
@@ -1202,7 +1292,30 @@ print_nhm_turbo_ratio_limits:
 	if (ratio)
 		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 1 active cores\n",
 			ratio, bclk, ratio * bclk);
+	return;
+}
+
+static void
+dump_nhm_cst_cfg(void)
+{
+	unsigned long long msr;
+
+	get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+
+#define SNB_C1_AUTO_UNDEMOTE              (1UL << 27)
+#define SNB_C3_AUTO_UNDEMOTE              (1UL << 28)
 
+	fprintf(stderr, "cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", msr);
+
+	fprintf(stderr, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
+		(msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
+		(msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "",
+		(msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "",
+		(msr & NHM_C1_AUTO_DEMOTE) ? "demote-C1, " : "",
+		(msr & (1 << 15)) ? "" : "UN",
+		(unsigned int)msr & 7,
+		pkg_cstate_limit_strings[pkg_cstate_limit]);
+	return;
 }
 
 void free_all_buffers(void)
@@ -1483,7 +1596,8 @@ void check_dev_msr()
 	struct stat sb;
 
 	if (stat("/dev/cpu/0/msr", &sb))
-		err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
+ 		if (system("/sbin/modprobe msr > /dev/null 2>&1"))
+			err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
 }
 
 void check_permissions()
@@ -1573,6 +1687,8 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	case 0x47:	/* BDW */
 	case 0x4F:	/* BDX */
 	case 0x56:	/* BDX-DE */
+	case 0x4E:	/* SKL */
+	case 0x5E:	/* SKL */
 		pkg_cstate_limits = hsw_pkg_cstate_limits;
 		break;
 	case 0x37:	/* BYT */
@@ -1590,7 +1706,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	}
 	get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
 
-	pkg_cstate_limit = pkg_cstate_limits[msr & 0x7];
+	pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
 
 	return 1;
 }
@@ -1615,12 +1731,49 @@ int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model)
 
 	switch (model) {
 	case 0x3E:	/* IVB Xeon */
+	case 0x3F:	/* HSW Xeon */
+		return 1;
+	default:
+		return 0;
+	}
+}
+int has_hsw_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+	if (!genuine_intel)
+		return 0;
+
+	if (family != 6)
+		return 0;
+
+	switch (model) {
+	case 0x3F:	/* HSW Xeon */
 		return 1;
 	default:
 		return 0;
 	}
 }
 
+static void
+dump_cstate_pstate_config_info(family, model)
+{
+	if (!do_nhm_platform_info)
+		return;
+
+	dump_nhm_platform_info();
+
+	if (has_hsw_turbo_ratio_limit(family, model))
+		dump_hsw_turbo_ratio_limits();
+
+	if (has_ivt_turbo_ratio_limit(family, model))
+		dump_ivt_turbo_ratio_limits();
+
+	if (has_nhm_turbo_ratio_limit(family, model))
+		dump_nhm_turbo_ratio_limits();
+
+	dump_nhm_cst_cfg();
+}
+
+
 /*
  * print_epb()
  * Decode the ENERGY_PERF_BIAS MSR
@@ -1690,35 +1843,35 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 		get_msr(cpu, MSR_CORE_PERF_LIMIT_REASONS, &msr);
 		fprintf(stderr, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
 		fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)",
-			(msr & 1 << 0) ? "PROCHOT, " : "",
-			(msr & 1 << 1) ? "ThermStatus, " : "",
-			(msr & 1 << 2) ? "bit2, " : "",
-			(msr & 1 << 4) ? "Graphics, " : "",
-			(msr & 1 << 5) ? "Auto-HWP, " : "",
-			(msr & 1 << 6) ? "VR-Therm, " : "",
-			(msr & 1 << 8) ? "Amps, " : "",
-			(msr & 1 << 9) ? "CorePwr, " : "",
-			(msr & 1 << 10) ? "PkgPwrL1, " : "",
-			(msr & 1 << 11) ? "PkgPwrL2, " : "",
-			(msr & 1 << 12) ? "MultiCoreTurbo, " : "",
-			(msr & 1 << 13) ? "Transitions, " : "",
+			(msr & 1 << 15) ? "bit15, " : "",
 			(msr & 1 << 14) ? "bit14, " : "",
-			(msr & 1 << 15) ? "bit15, " : "");
+			(msr & 1 << 13) ? "Transitions, " : "",
+			(msr & 1 << 12) ? "MultiCoreTurbo, " : "",
+			(msr & 1 << 11) ? "PkgPwrL2, " : "",
+			(msr & 1 << 10) ? "PkgPwrL1, " : "",
+			(msr & 1 << 9) ? "CorePwr, " : "",
+			(msr & 1 << 8) ? "Amps, " : "",
+			(msr & 1 << 6) ? "VR-Therm, " : "",
+			(msr & 1 << 5) ? "Auto-HWP, " : "",
+			(msr & 1 << 4) ? "Graphics, " : "",
+			(msr & 1 << 2) ? "bit2, " : "",
+			(msr & 1 << 1) ? "ThermStatus, " : "",
+			(msr & 1 << 0) ? "PROCHOT, " : "");
 		fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)\n",
-			(msr & 1 << 16) ? "PROCHOT, " : "",
-			(msr & 1 << 17) ? "ThermStatus, " : "",
-			(msr & 1 << 18) ? "bit18, " : "",
-			(msr & 1 << 20) ? "Graphics, " : "",
-			(msr & 1 << 21) ? "Auto-HWP, " : "",
-			(msr & 1 << 22) ? "VR-Therm, " : "",
-			(msr & 1 << 24) ? "Amps, " : "",
-			(msr & 1 << 25) ? "CorePwr, " : "",
-			(msr & 1 << 26) ? "PkgPwrL1, " : "",
-			(msr & 1 << 27) ? "PkgPwrL2, " : "",
-			(msr & 1 << 28) ? "MultiCoreTurbo, " : "",
-			(msr & 1 << 29) ? "Transitions, " : "",
+			(msr & 1 << 31) ? "bit31, " : "",
 			(msr & 1 << 30) ? "bit30, " : "",
-			(msr & 1 << 31) ? "bit31, " : "");
+			(msr & 1 << 29) ? "Transitions, " : "",
+			(msr & 1 << 28) ? "MultiCoreTurbo, " : "",
+			(msr & 1 << 27) ? "PkgPwrL2, " : "",
+			(msr & 1 << 26) ? "PkgPwrL1, " : "",
+			(msr & 1 << 25) ? "CorePwr, " : "",
+			(msr & 1 << 24) ? "Amps, " : "",
+			(msr & 1 << 22) ? "VR-Therm, " : "",
+			(msr & 1 << 21) ? "Auto-HWP, " : "",
+			(msr & 1 << 20) ? "Graphics, " : "",
+			(msr & 1 << 18) ? "bit18, " : "",
+			(msr & 1 << 17) ? "ThermStatus, " : "",
+			(msr & 1 << 16) ? "PROCHOT, " : "");
 
 	}
 	if (do_gfx_perf_limit_reasons) {
@@ -1784,6 +1937,25 @@ double get_tdp(model)
 	}
 }
 
+/*
+ * rapl_dram_energy_units_probe()
+ * Energy units are either hard-coded, or come from RAPL Energy Unit MSR.
+ */
+static double
+rapl_dram_energy_units_probe(int  model, double rapl_energy_units)
+{
+	/* only called for genuine_intel, family 6 */
+
+	switch (model) {
+	case 0x3F:	/* HSX */
+	case 0x4F:	/* BDX */
+	case 0x56:	/* BDX-DE */
+		return (rapl_dram_energy_units = 15.3 / 1000000);
+	default:
+		return (rapl_energy_units);
+	}
+}
+
 
 /*
  * rapl_probe()
@@ -1812,14 +1984,18 @@ void rapl_probe(unsigned int family, unsigned int model)
 	case 0x47:	/* BDW */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		break;
+	case 0x4E:	/* SKL */
+	case 0x5E:	/* SKL */
+		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		break;
 	case 0x3F:	/* HSX */
 	case 0x4F:	/* BDX */
 	case 0x56:	/* BDX-DE */
-		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
 	case 0x2D:
 	case 0x3E:
-		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
 	case 0x37:	/* BYT */
 	case 0x4D:	/* AVN */
@@ -1839,6 +2015,8 @@ void rapl_probe(unsigned int family, unsigned int model)
 	else
 		rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F));
 
+	rapl_dram_energy_units = rapl_dram_energy_units_probe(model, rapl_energy_units);
+
 	time_unit = msr >> 16 & 0xF;
 	if (time_unit == 0)
 		time_unit = 0xA;
@@ -2009,19 +2187,18 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			((msr >> 48) & 1) ? "EN" : "DIS");
 	}
 
-	if (do_rapl & RAPL_DRAM) {
+	if (do_rapl & RAPL_DRAM_POWER_INFO) {
 		if (get_msr(cpu, MSR_DRAM_POWER_INFO, &msr))
                 	return -6;
 
-
 		fprintf(stderr, "cpu%d: MSR_DRAM_POWER_INFO,: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
 			cpu, msr,
 			((msr >>  0) & RAPL_POWER_GRANULARITY) * rapl_power_units,
 			((msr >> 16) & RAPL_POWER_GRANULARITY) * rapl_power_units,
 			((msr >> 32) & RAPL_POWER_GRANULARITY) * rapl_power_units,
 			((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units);
-
-
+	}
+	if (do_rapl & RAPL_DRAM) {
 		if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr))
 			return -9;
 		fprintf(stderr, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
@@ -2090,6 +2267,8 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 	case 0x47:	/* BDW */
 	case 0x4F:	/* BDX */
 	case 0x56:	/* BDX-DE */
+	case 0x4E:	/* SKL */
+	case 0x5E:	/* SKL */
 		return 1;
 	}
 	return 0;
@@ -2110,11 +2289,35 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
 	switch (model) {
 	case 0x45:	/* HSW */
 	case 0x3D:	/* BDW */
+	case 0x4E:	/* SKL */
+	case 0x5E:	/* SKL */
 		return 1;
 	}
 	return 0;
 }
 
+/*
+ * SKL adds support for additional MSRS:
+ *
+ * MSR_PKG_WEIGHTED_CORE_C0_RES    0x00000658
+ * MSR_PKG_ANY_CORE_C0_RES         0x00000659
+ * MSR_PKG_ANY_GFXE_C0_RES         0x0000065A
+ * MSR_PKG_BOTH_CORE_GFXE_C0_RES   0x0000065B
+ */
+int has_skl_msrs(unsigned int family, unsigned int model)
+{
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case 0x4E:	/* SKL */
+	case 0x5E:	/* SKL */
+		return 1;
+	}
+	return 0;
+}
+
+
 
 int is_slm(unsigned int family, unsigned int model)
 {
@@ -2228,7 +2431,7 @@ guess:
 
 	return 0;
 }
-void check_cpuid()
+void process_cpuid()
 {
 	unsigned int eax, ebx, ecx, edx, max_level;
 	unsigned int fms, family, model, stepping;
@@ -2294,6 +2497,41 @@ void check_cpuid()
 			do_ptm ? "" : "No ",
 			has_epb ? "" : "No ");
 
+	if (max_level > 0x15) {
+		unsigned int eax_crystal;
+		unsigned int ebx_tsc;
+
+		/*
+		 * CPUID 15H TSC/Crystal ratio, possibly Crystal Hz
+		 */
+		eax_crystal = ebx_tsc = crystal_hz = edx = 0;
+		__get_cpuid(0x15, &eax_crystal, &ebx_tsc, &crystal_hz, &edx);
+
+		if (ebx_tsc != 0) {
+
+			if (debug && (ebx != 0))
+				fprintf(stderr, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n",
+					eax_crystal, ebx_tsc, crystal_hz);
+
+			if (crystal_hz == 0)
+				switch(model) {
+				case 0x4E:	/* SKL */
+				case 0x5E:	/* SKL */
+					crystal_hz = 24000000;	/* 24 MHz */
+					break;
+				default:
+					crystal_hz = 0;
+			}
+
+			if (crystal_hz) {
+				tsc_hz =  (unsigned long long) crystal_hz * ebx_tsc / eax_crystal;
+				if (debug)
+					fprintf(stderr, "TSC: %lld MHz (%d Hz * %d / %d / 1000000)\n",
+						tsc_hz / 1000000, crystal_hz, ebx_tsc,  eax_crystal);
+			}
+		}
+	}
+
 	do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
 	do_snb_cstates = has_snb_msrs(family, model);
 	do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
@@ -2301,18 +2539,19 @@ void check_cpuid()
 	do_pc6 = (pkg_cstate_limit >= PCL__6);
 	do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7);
 	do_c8_c9_c10 = has_hsw_msrs(family, model);
+	do_skl_residency = has_skl_msrs(family, model);
 	do_slm_cstates = is_slm(family, model);
 	bclk = discover_bclk(family, model);
 
-	do_nhm_turbo_ratio_limit = do_nhm_platform_info && has_nhm_turbo_ratio_limit(family, model);
-	do_ivt_turbo_ratio_limit = has_ivt_turbo_ratio_limit(family, model);
 	rapl_probe(family, model);
 	perf_limit_reasons_probe(family, model);
 
+	if (debug)
+		dump_cstate_pstate_config_info();
+
 	return;
 }
 
-
 void help()
 {
 	fprintf(stderr,
@@ -2428,14 +2667,14 @@ void topology_probe()
 	if (debug > 1)
 		fprintf(stderr, "max_core_id %d, sizing for %d cores per package\n",
 			max_core_id, topo.num_cores_per_pkg);
-	if (!summary_only && topo.num_cores_per_pkg > 1)
+	if (debug && !summary_only && topo.num_cores_per_pkg > 1)
 		show_core = 1;
 
 	topo.num_packages = max_package_id + 1;
 	if (debug > 1)
 		fprintf(stderr, "max_package_id %d, sizing for %d packages\n",
 			max_package_id, topo.num_packages);
-	if (!summary_only && topo.num_packages > 1)
+	if (debug && !summary_only && topo.num_packages > 1)
 		show_pkg = 1;
 
 	topo.num_threads_per_core = max_siblings;
@@ -2550,14 +2789,11 @@ void turbostat_init()
 {
 	check_dev_msr();
 	check_permissions();
-	check_cpuid();
+	process_cpuid();
 
 	setup_all_buffers();
 
 	if (debug)
-		print_verbose_header();
-
-	if (debug)
 		for_all_cpus(print_epb, ODD_COUNTERS);
 
 	if (debug)
@@ -2634,7 +2870,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(stderr, "turbostat version 4.1 10-Feb, 2015"
+	fprintf(stderr, "turbostat version 4.5 2 Apr, 2015"
 		" - Len Brown <lenb@kernel.org>\n");
 }